metadata

license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: Mistral-7B-Instruct-KhanAcademy-v0.2
    results: []

See axolotl config

axolotl version: 0.4.0

base_model: mistralai/Mistral-7B-Instruct-v0.2
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true


hub_model_id: MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: CohereForAI/aya_dataset
    type:
      system_prompt: ""
      field_instruction: inputs
      field_output: targets
      format: "[INST] {instruction} [/INST]"
      no_input_format: "[INST] {instruction} [/INST]"

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./models/MaziyarPanahi/Mistral-7B-Instruct-Aya-101

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

Mistral-7B-Instruct-KhanAcademy-v0.2

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.1502

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.9039	0.0	1	3.1495
0.9933	0.25	101	1.2402
0.9439	0.5	202	1.1683
0.9762	0.75	303	1.1502

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.2.0+cu121
Datasets 2.17.0
Tokenizers 0.15.0